© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4873
    Prev
    Next
    INDEX
    Explanations

    words related to advancement or progression in a project or process

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    0.8%
    442
    +0.09
    0.3%
    1059
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1396
    +0.19
    0.03
    200
    +0.09
    0.04
    1079
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.32
    public
    -0.58
    /*!
    -0.55
     visit
    -0.52
    /***
    -0.52
    集
    -0.51
     find
    -0.51
    declare
    -0.50
    Argumento
    -0.50
     swore
    -0.50
    POSITIVE LOGITS
     panama
    1.08
     stockholm
    1.06
     ecru
    1.03
     tricot
    1.01
     maroc
    1.01
     venice
    1.00
     frankfurt
    1.00
     affez
    1.00
     incess
    0.99
     chicco
    0.98
    Activations Density 0.502%

    No Known Activations